构建模拟交易多智能体系统，提升投资策略评估能力
QuantAgents: Towards Multi-agent Financial System via Simulated Trading
- 四类智能体协同决策，通过模拟交易评估策略
- 三年综合收益近300%，优于现有方法
- 适合量化金融研究与智能投顾开发人员
本文旨在构建一个融合模拟交易的多智能体金融系统，以弥补当前基于大模型的代理在真实基金公司运作中的差距。关键差异在于现有模型依赖‘事后反思’应对不利结果，却缺乏人类特有的长期趋势预测能力。为此，我们提出QuantAgents，包含模拟交易分析师、风控分析师、市场新闻分析师和管理者四类智能体，通过多轮协作会议共同决策。系统从两个维度激励智能体：真实市场表现和模拟交易预测准确性。大量实验表明，该框架在各项指标上均表现优异，三年总回报率接近300%（https://quantagents.github.io/）。
原文摘要 · Abstract (English)
In this paper, our objective is to develop a multi-agent financial system that incorporates simulated trading, a technique extensively utilized by financial professionals. While current LLM-based agent models demonstrate competitive performance, they still exhibit significant deviations from real-world fund companies. A critical distinction lies in the agents' reliance on ``post-reflection'', particularly in response to adverse outcomes, but lack a distinctly human capability: long-term prediction of future trends. Therefore, we introduce QuantAgents, a multi-agent system integrating simulated trading, to comprehensively evaluate various investment strategies and market scenarios without assuming actual risks. Specifically, QuantAgents comprises four agents: a simulated trading analyst, a risk control analyst, a market news analyst, and a manager, who collaborate through several meetings. Moreover, our system incentivizes agents to receive feedback on two fronts: performance in real-world markets and predictive accuracy in simulated trading. Extensive experiments demonstrate that our framework excels across all metrics, yielding an overall return of nearly 300% over the three years (https://quantagents.github.io/).
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。